© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81097
    Prev
    Next
    INDEX
    Explanations

    school explosion

    np_acts-logits-general · gemini-2.5-flash-lite

    glancing at, exploit is, invoice number exist, She sighs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sust
    0.40
    č
    0.40
    r
    0.40
    inn
    0.40
    4
    0.40
     monk
    0.39
    i
    0.39
    דו
    0.39
    translational
    0.39
    d
    0.39
    POSITIVE LOGITS
     آتے
    0.50
     அற
    0.48
     同じ
    0.47
    ッキー
    0.46
    ብሰ
    0.46
     おい
    0.46
     commandes
    0.45
     इकट
    0.43
    انک
    0.43
     legales
    0.42
    Activations Density 0.002%

    No Known Activations